FAQ

Last modified:
Q: How to register this course?

You DON'T need my permission and can do it online by yourself after the semester starts.


Q: Who should not take this course?

We aim to learn algorithms and implementations for deep learning. Thus if you only would like to use deep learning for applications, this is not a course to take.

In a way you can think that we position ourselves as those who build existing deep learning tools.


Q: Where can I find the course information?

Please check the course web page.

The easiest way to find the course page is to search my name. On my homepage there is a section "Courses." It's listed there.


Q: What is the difference between this course and a related course you offered in the past?

In the past we focused more on optimization algorithms for deep learning. But in the current course, we pay more attention to the implementation of deep learning systems.


Q: What's the needed knowledge for taking this course?

You should have basic understanding of calculus and linear algebra, and good programming skill.


Q: For projects, do we split students to groups for doing them?

It's not clear yet at this moment. Things depend on

What I can say now is that the final project presentations are a very important component of this course. We expect fruitful discussion there.
Q: How should I submit my project report?

We will use NTU COOL system for your project submission. No late submission will be accepted.


Q: How about the format of the report?

Progress report should be at most 6 pages, while the final report may be up to twenty pages, including references. Use the latex template here. See the resulting pdf.

Please submit one pdf file only. No other files. No sub-directories.


Q: What if I don't use the template for the project report?

You get zero point.


Q: Some additional policy to be reminded here?

When using outside resources, proper citation is necessary. This includes papers, text books, software libraries, websites, and helps from others.

Discussion is perfectly fine.

Please state what you have done. No fake results and no exaggeration. For doing research, failure is an option


Q: Can you say a bit about grading?

For every report or presentation you will get a score. In the end we do a weighted average.

For the project report you must pay attention to the writing and the organization. If a report is badly written, no matter how great your results are, you get a low score.


Q: What's the formula to calculate your grade?

Depending on your performance, we decide the distribution of your grades. That is, how many get A+ and how many get F-. Then, we calculate raw scores, obtain a ranking of students, and assign their grades.

So there is no direct relationship between your raw score and your grade. It is possible that your raw score is 99, but you get F-.


Q: How about computing resources for doing projects?

We assume that you can find computing resources needed for your projects


Q: I spot an error on the teacher's slides. What should I do?

Please email me. Any improvements on slides will be useful to students in the future.


Q: I am very interested in topics related to this course. Could I have continuing research discussion with you even after the end of this course?

Yes, absolutely.


Please contact Chih-Jen Lin for any question.